Accurate global solar radiation prediction is highly essential for related research on renewable energy sources. The cost implication and measurement expertise of global solar radiation emphasize that intelligence prediction models need to be applied. On the basis of long-term measured daily solar radiation data, this study uses a novel regularized online sequential extreme learning machine, integrated with variable forgetting factor (FOS-ELM), to predict global solar radiation at Bur Dedougou, in the Burkina Faso region. Bayesian Information Criterion (BIC) is applied to build the seven input combinations based on speed (W_speed), maximum and minimum temperature (T_max and T_min), maximum and minimum humidity (H_max and H_min), evaporation (E_o) and vapor pressure deficiency (V_PD). For the difference input parameters magnitudes, seven models were developed and evaluated for the optimal input combination. Various statistical indicators were computed for the prediction accuracy examination. The experimental results of the applied FOS-ELM model demonstrated a reliable prediction accuracy against the classical extreme learning machine (ELM) model for daily global solar radiation simulation. In fact, compared to classical ELM, the FOS-ELM model reported an enhancement in the root mean square error (RMSE) and mean absolute error (MAE) by (68.8–79.8%). In summary, the results clearly confirm the effectiveness of the FOS-ELM model, owing to the fixed internal tuning parameters.

Objectives: To investigate the clinical value of contrast-enhanced CT combined with PET/CT in the differential diagnosis of mediastinal lymph node metastasis (MLNM) of non-small-cell lung cancer (NSCLC). Methods: A total of 120 patients with NSCLC combined with mediastinal lymphadenopathy hospitalized in our hospital were selected. All the patients received radical resection of lung cancer and mediastinal lymphadenectomy. After pathological diagnosis, they were divided into MLNM group (malignant group, undergoing contrast-enhanced CT) and non-MLNM group (benign group, receiving contrast-enhanced CT combined with PET-CT). The results were judged by two senior radiologists independently. The results of different scanning methods and postoperative pathology were compared using the t test, χ2 test and Pearson correlation coefficient test. Results: Compared with the pathological results, contrast-enhanced CT diagnosed 31 cases, with a coincidence rate of 62%, and contrast-enhanced CT combined with PET-CT diagnosed 42 cases, with a coincidence rate of 84%, presenting a statistically significant difference (P = 0.02). Among the 120 patients with lung cancer, pathological examination confirmed MLNM in 50 patients and benign enlargement in 70 patients, contrast-enhanced CT alone detected metastasis in 40 patients and benign enlargement in 80 patients, and contrast-enhanced CT combined with PET-CT detected metastasis in 47 patients and benign enlargement in 73 patients. The sensitivity and accuracy of the latter were significantly higher than those of the former (sensitivity, P = 0.01; accuracy, P = 0.01). With the increase in the malignancy of lymph nodes, the degree of CT enhancement, the concentration of radioactive substances and SUV value increased, showing positive correlations. Conclusion: Contrast-enhanced CT combined with PET/CT in the diagnosis of MLNM of NSCLC presents higher coincidence rate, sensitivity and accuracy. With the increase in tumor malignancy, the enhancement degree and radioactive substance concentration increase. The two methods are synergistic and complementary in diagnosing MLNM. doi: https://doi.org/10.12669/pjms.38.5.5528 How to cite this:Li X, Zheng X, Zhang T, Dong X, Su J. Clinical evaluation of contrast-enhanced CT combined with PET/CT in diagnosis of mediastinal lymph node metastasis of non-small-cell lung cancer. Pak J Med Sci. 2022;38(5):1343-1348. doi: https://doi.org/10.12669/pjms.38.5.5528 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Classifying land-use scenes with high quality and accuracy is an important research direction in current hyperspectral remote sensing images, which is conducive to scientific management and utilization of land. An effective classifier and feature extractor can improve classification stability and accuracy. Therefore, based on deep learning technique, a dropout-based ensemble learning method is proposed in this paper, which combines convolutional neural network (CNN) and information discriminating extreme learning machine (IELM). Pre-trained CNN is used to learn effective and robust features, and deep convolution features are fed to the IELM classifier. Then the adoption of dropout technique and ensemble method can improve generalization capabilities and stability. The effectiveness of the proposed algorithm is tested by hyperspectral remote sensing image classification experiments. The experimental results show that the proposed E-CNN-dropIELM has achieved satisfactory results compared to state-of-the-art methods in terms of classification accuracy and stability.